Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to actions or activities, especially those involving physical movement or interaction

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gameplay or sports participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unden
    -0.73
     gobl
    -0.70
     Sabha
    -0.69
     Citiz
    -0.69
     notor
    -0.67
     bowel
    -0.66
    ãĥ£
    -0.65
    ISO
    -0.64
     diam
    -0.63
    bestos
    -0.63
    POSITIVE LOGITS
    ingly
    0.99
    ables
    0.98
    ers
    0.97
    orship
    0.97
    rers
    0.89
    ments
    0.88
    ery
    0.86
    eria
    0.86
    enges
    0.86
    er
    0.85
    Act Density 0.104%

    No Known Activations